Follow Discord
Sweep 25 Sep 2026 · 19:33Z Build v2.1.283 504 read Stable v2.1.274 Latest v2.1.283 Next v2.1.283 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.283 ·

Auto mode can check Claude-in-Chrome clicks, behind a remote setting that defaults to off

A new classifyChromeClicks setting can route Claude-in-Chrome clicks through the auto-mode classifier, as navigation already is

Group of 2 You'll notice Notable Nothing to try yet No documentation found In Development
JSON All of v2.1.283
You'll noticeTier: how much it should matter to you
3Useful: my rating, 1 to 5
4Signal: worth watching, 1 to 5
Auto ModeArea: what it touches
In DevelopmentKind: in v2.1.283,
What probably matters to youSection of the release

What

In auto mode, a classifier (a model that judges whether an action is safe) decides some permission requests for you. Claude in Chrome already sent page navigations to it. A new setting can send clicks too:

  • The permission settings gain chromeClickClassifierEnabled, next to the existing chromeNavigationClassifierEnabled.
  • It is on only when the remote configuration tengu_auto_mode_config has classifyChromeClicks set to exactly true. Otherwise it stays off.
  • The clicks covered are left_click, right_click, middle_click, double_click, triple_click and left_click_drag, whether sent alone on the computer tool or inside a batched actions list.
  • When it applies, a click is treated as an action for the classifier, the same way Chrome navigation already is.

No reading of tengu_auto_mode_config has been taken under this release yet.

Why

Once the server turns this on, browser clicks in auto mode would be checked by the safety classifier as well as page loads.

Read from
Names in the bundleclassifyChromeClicks
Feature flag
tengu_auto_mode_config Not enough to say

Nothing here resolved what this flag was doing on this version, so nothing here should be read as on or off.

This account: no value returned · anonymous baseline: no value returned · compiled default in v2.1.283: not a boolean we can read

These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.

Read once, for one account on one subscription tier, against v2.1.283. It isn't a statement about your account. What a flag value here can and cannot tell you

What has happened since
Flag reading moved The flag server now returns {"editRemovalCap":3000,"editRemovalVisibility":true,"enabled":"enabled","envOnboarding":true,"gitStatusType":true,"gitStatusUploads":false,"jsonlTranscript":true,"outcomeVisibility":false,"repoVisibility":true,"sameTurnSiblingContext":true,"severityByModel":{"claude-opus-4-8":{"t1":45,"t2":35},"claude-opus-4-8[1m]":{"t1":45,"t2":35},"claude-sonnet-5":{"t1":25,"t2":35},"claude-sonnet-5[1m]":{"t1":25,"t2":35}},"severityBySite":{"compactFabCheck":"on","handoff":"on","investigator":"on","sandboxNetwork":"on","workflowGate":"on"},"twoStageClassifier":true} for tengu_auto_mode_config, read as this account. A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
Flag reading moved The flag server now returns {"editRemovalCap":3000,"editRemovalVisibility":true,"enabled":"enabled","gitStatusType":true,"gitStatusUploads":false,"jsonlTranscript":true,"outcomeVisibility":false,"repoVisibility":true,"sameTurnSiblingContext":true,"severityByModel":{"claude-opus-4-8":{"t1":45,"t2":35},"claude-opus-4-8[1m]":{"t1":45,"t2":35},"claude-sonnet-5":{"t1":25,"t2":35},"claude-sonnet-5[1m]":{"t1":25,"t2":35}},"severityBySite":{"compactFabCheck":"on","handoff":"on","investigator":"on","sandboxNetwork":"on","workflowGate":"on"},"twoStageClassifier":true} for tengu_auto_mode_config, read as this account. A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
Flag reading moved The flag server now returns {"editRemovalCap":3000,"editRemovalVisibility":true,"enabled":"enabled","envOnboarding":true,"gitStatusType":true,"gitStatusUploads":false,"jsonlTranscript":true,"outcomeVisibility":false,"repoVisibility":true,"sameTurnSiblingContext":true,"severityByModel":{"claude-opus-4-8":{"t1":45,"t2":35},"claude-opus-4-8[1m]":{"t1":45,"t2":35},"claude-sonnet-5":{"t1":25,"t2":35},"claude-sonnet-5[1m]":{"t1":25,"t2":35}},"severityBySite":{"compactFabCheck":"on","handoff":"on","investigator":"on","sandboxNetwork":"on","workflowGate":"on"},"twoStageClassifier":true} for tengu_auto_mode_config, read as this account. A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
Flag reading moved The flag server now returns {"editRemovalCap":3000,"editRemovalVisibility":true,"enabled":"enabled","gitStatusType":true,"gitStatusUploads":false,"jsonlTranscript":true,"outcomeVisibility":false,"repoVisibility":true,"sameTurnSiblingContext":true,"severityByModel":{"claude-opus-4-8":{"t1":45,"t2":35},"claude-opus-4-8[1m]":{"t1":45,"t2":35},"claude-sonnet-5":{"t1":25,"t2":35},"claude-sonnet-5[1m]":{"t1":25,"t2":35}},"severityBySite":{"compactFabCheck":"on","handoff":"on","investigator":"on","sandboxNetwork":"on","workflowGate":"on"},"twoStageClassifier":true} for tengu_auto_mode_config, read as this account. A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
Flag reading moved The flag server now returns {"editRemovalCap":3000,"editRemovalVisibility":true,"enabled":"enabled","envOnboarding":true,"gitStatusType":true,"gitStatusUploads":false,"jsonlTranscript":true,"outcomeVisibility":false,"repoVisibility":true,"sameTurnSiblingContext":true,"severityByModel":{"claude-opus-4-8":{"t1":45,"t2":35},"claude-opus-4-8[1m]":{"t1":45,"t2":35},"claude-sonnet-5":{"t1":25,"t2":35},"claude-sonnet-5[1m]":{"t1":25,"t2":35}},"severityBySite":{"compactFabCheck":"on","handoff":"on","investigator":"on","sandboxNetwork":"on","workflowGate":"on"},"twoStageClassifier":true} for tengu_auto_mode_config, read as this account. A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.

See this across every release →

How sure we are
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubtWhat uses the new setting was not checked.

See this entry in the whole of v2.1.283 →

Feedback